An Experimental Study on Competitive Coevolution of MLP Classifiers
Abstract
This paper investigates the effectiveness and efficiency of two competitive (predator-prey) evolutionary
procedures for training multi-layer perceptron classifiers: Co-Adaptive Neural Network Training, and a modified
version of Co-Evolutionary Neural Network Training. The study focused on how the performance of the two procedures varies as the size of the training set increases, and their ability to redress class imbalance problems of increasing severity. Compared to the customary backpropagation algorithm and a standard evolutionary algorithm, the two competitive procedures excelled in terms of quality of the solutions and execution speed. Co-Adaptive Neural Network Training excelled on class imbalance problems, and on classification problems of moderately large training sets. Co-Evolutionary Neural Network Training performed best on the largest data sets. The size of the training set was the most problematic issue for the backpropagation algorithm and the standard evolutionary algorithm, respectively in terms of accuracy of the solutions and execution speed. Backpropagation and the evolutionary algorithm were also not competitive on the class imbalance problems, where data oversampling could only partially remedy their shortcomings.
References
Haykin, S.: Neural Networks and Learning Machines, 3rd edn. Prentice Hall, New York, USA (2009).
Rumelhart, D., McClelland, J.: Parallel distributed processing: explorations in the microstructure of cognition, vol. 1-2, MIT Press, Cambridge, USA (1986).
Yao, X.: Evolving Artificial Neural Networks. Proceedings IEEE 87(9), pp. 1423-1447 (1999).
Castellani, M.: Evolutionary Generation of Neural Network Classifiers - An Empirical Comparison. Neurocomputing 99, pp. 214-229 (2013)
Paredis, J.: Coevolutionary life-time learning. In: I. Rechenberg and H.P. Schwefel (ed.) Parallel Problem Solving from Nature - PPSN IV, pp. 72-80. Springer, Berlin Heidelberg, (1996).
Paredis, J.: Coevolutionary computation. Artificial life 2(4), pp. 355-375 (1995).
Whitley, D.: The Genitor algorithm and selection pressure: why rank-based allocation of reproductive trails is best. In: JD Schaffer (ed.) Proceedings of the Third International Conference on Genetic Algorithms, pp. 116-123. San Mateo, CA, Morgan Kaufmann Publishers, San Francisco, USA (1989).
Castellani, M.: Competitive co-evolution of multi-layer perceptron classifiers. Soft Computing, published online (2017). DOI 10.1007/s00500-017-2587-6
Weiss, G.M.: Mining with rarity: a unifying framework. ACM SIGKDD Explorations Newsletter 6(1), pp. 7-19 (2004).
Popovici, E., Bucci, A., Wiegand, R.P., De Jong, E.D.: Coevolutionary principles. In: G. Rozenberg et al. (ed.) Handbook of Natural Computing, pp. 987-1033. Springer, Berlin Heidelberg (2012).
Pollack, J.B., Blair, A.D.: Co-evolution in the successful learning of backgammon strategy. Machine Learning 32(3), pp. 225-240 (1998).
Fogel, D.B.: Evolutionary computation: toward a new philosophy of machine intelligence, 2nd edn. IEEE Press, New York, USA (2000).
MENDEL open access articles are normally published under a Creative Commons Attribution-NonCommercial-ShareAlike (CC BY-NC-SA 4.0) https://creativecommons.org/licenses/by-nc-sa/4.0/ . Under the CC BY-NC-SA 4.0 license permitted 3rd party reuse is only applicable for non-commercial purposes. Articles posted under the CC BY-NC-SA 4.0 license allow users to share, copy, and redistribute the material in any medium of format, and adapt, remix, transform, and build upon the material for any purpose. Reusing under the CC BY-NC-SA 4.0 license requires that appropriate attribution to the source of the material must be included along with a link to the license, with any changes made to the original material indicated.
